Comparative Evaluation of Machine Learning Techniques for Breast Cancer Detection

Breast cancer is a primary cause of death for women. Millions of women worldwide were suspected with breast cancer diagnosis in 2022. But early-stage breast cancer is still treatable. Patients' recoveries become better when breast cancer is discovered early and treated quickly and efficiently. Machine learning algorithms have become an effective tool for precisely and successfully diagnosing breast cancer in recent years. This research focuses on the utilization of machine learning (ML) techniques. To achieve this, we looked into a variety of machine learning methods including XGBoost, Random Forest, K Nearest Neighbours, Naïve Bayes, Decision Trees, Logistic Regression, and Neural Networks. Metrics including accuracy, precision, F1score, recall, and balanced accuracy were used as indicators of the models. The result shows that K Nearest Neighbors and Naïve Bayes has more accuracy and can be effective in early detection of cancer.